#!/usr/bin/env python
# coding: utf-8

# Copyright © 2007 Forest Bond.

# This program may be distributed according to the terms of the GNU General
# Public License version 2.  See http://www.gnu.org/licenses/gpl-2.0.html for
# the full text of the license.

'''\
${name} [options] {codepoint|charname} ...

Options:
  -v, --version         Print version info to standard output.
  -h, --help            Print this text to standard output.

Examples:
  ${name} bullet
  •

  ${name} 'greek capital letter delta' 'greek capital letter phi' \\
    'greek capital letter sigma'
  ΔΦΣ
'''

__self__ = 'unichar'
__author__ = 'Forest Bond <forest@alittletooquiet.net>'
__version__ = '0.2'
__copyright__ = '© 2007'
__license__ = 'GPL version 2'

import sys, locale, unicodedata
import sclapp

def guessTerminalEncoding():
    return locale.getpreferredencoding()

def handle_argv(argv):
    if len(argv) < 2:
        raise sclapp.UsageError, 'Too few arguments'
    return [ a.strip() for a in argv[1:] ]

def parseIdentifier(identifier):
    try:
        return 'codepoint', int(identifier)
    except (ValueError, TypeError):
        pass

    try:
        return 'codepoint', int(identifier, 16)
    except (ValueError, TypeError):
        pass

    if (len(identifier) > 2) and (identifier[:2].lower() == 'u+'):
        try:
            val = int(identifier[2:], 16)
        except (ValueError, TypeError):
            pass
        else:
            return 'codepoint', val

    return 'name', identifier.upper()

def getUnicodeCharacter(identifier):
    identifier_type, identifier = parseIdentifier(identifier)

    if identifier_type == 'codepoint':
        return getUnicodeCharacterByCodepoint(identifier)
    elif identifier_type == 'name':
        return getUnicodeCharacterByName(identifier)
    raise ValueError, 'Identifier could not be parsed'

def getUnicodeCharacterByCodepoint(codepoint):
    try:
        return unichr(codepoint)
    except ValueError:
        raise ValueError, (
          'No Unicode character with code point U+%X' % codepoint)

def getUnicodeCharacterByName(name):
    try:
        return unicodedata.lookup(name)
    except KeyError:
        raise ValueError, 'No Unicode character named "%s"' % name

def printUnicodeCharacter(identifier):
    # This depends upon sclapp's handling of unicode characters written to
    # stdout, which should result in the unicode string being encoded properly:
    sys.stdout.write(getUnicodeCharacter(identifier))

@sclapp.main_function(
  name = __self__,
  version = __version__,
  doc = __doc__,
  error_output_level = sclapp.WARNING
)
def main(argv):
    identifiers = handle_argv(argv)

    success = True

    for identifier in identifiers:
        try:
            printUnicodeCharacter(identifier)
        except ValueError, e:
            print >>sys.stderr, str(e)
            success = False

    return int(not success)

if __name__ == '__main__':
    sys.exit(main())